Skip to content
View kiranosora's full-sized avatar

Block or report kiranosora

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型,任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型,单并发20tps;INT4量化模型单并发30tps,多并发可达60+。

C++ 4,174 416 Updated Mar 19, 2026

Simple frontend for LLMs built in react-native.

TypeScript 2,204 185 Updated Mar 9, 2026

fork自BilibiliVideoDownload, 为了修复已知bug

TypeScript 146 17 Updated Nov 27, 2025

A guide to help developers get up and running quickly with the OpenCL programming framework

CMake 681 70 Updated Aug 7, 2024

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Python 3,728 469 Updated Oct 12, 2023

李宏毅2021/2022/2023春季机器学习课程课件及作业

Jupyter Notebook 7,035 1,678 Updated Jun 3, 2023

总结梳理自然语言处理工程师(NLP)需要积累的各方面知识,包括面试题,各种基础知识,工程能力等等,提升核心竞争力

Python 7,476 1,204 Updated Aug 24, 2022

A Word2Vec_Implementation in python using numpy

Jupyter Notebook 8 18 Updated May 13, 2020

使用python-opencv识别图片中的表格数据转换为csv

Python 113 33 Updated May 5, 2020